πΏππππ π·ππππππ
@tylerl404
Followers
193
Following
947
Media
23
Statuses
352
NLP/AI PhD @ Sheffield | Prev: Forensic Speech Science @ York & Linguistics @ Huddersfield | The Tattooed Academic π€·ββοΈ
United Kingdom
Joined August 2012
2 weeks, 2 conferences, 2 posters on computational humour π«‘ Once again proving I'll be a graphic designer if this whole "AI" thing doesn't work out π€·ββοΈ #INLG2025 #EMNLP2025
0
0
2
Happy to announce our journal paper on tongue twisters, Train and Constrain (TwistList 2.0), has now been officially published in @CompLingJournal! (Thanks to @chenghua_lin and Chen Tang) https://t.co/ecAgSa6vxcβ¦
@sltcdt #nlp #nlproc #nlg
2
4
9
Weβre introducing 10% tariffs on all students not from Yorkshire (and 20% on students from Norfolk).
3
14
103
My PhD student Tyler (@tylerl404) is presenting 2 of our 6 papers at #EMNLP2024. In addition to being outstanding in research, he also has a great talent for design, as you can see from his fantastic posters! π
0
5
21
Weβre pleased to share that the Manchester NLP Group will be presenting *11 papers* at #EMNLP2024. Feel free to drop by and chat with our students and colleagues during their poster sessions and presentations! ππ» @csmcr @manchester_nlp
1
13
23
With Ears to See and Eyes to Hear: Sound Symbolism Experiments with Multimodal Large Language Models @tylerl404 @liyucheng_2 @chenghua_lin
https://t.co/cdDYtQhZ7H
1
1
4
MMTE: Corpus and Metrics for Evaluating Machine Translation Quality of Metaphorical Language @SWangMB @tylerl404 @chenghua_lin
https://t.co/61thRAcq9P
1
1
3
"MMTE: Corpus and Metrics for Evaluating Machine Translation Quality of Metaphorical Language" (main) @SWangMB @GeZhang86038849 @tylerl404 @chenghua_lin
https://t.co/HzMkXbc1LN
1
1
3
"Train & Constrain: Phonologically Informed Tongue-Twister Generation from Topics and Paraphrases" (Computational Linguistics) @tylerl404 @chenghua_lin
https://t.co/K9nQVl64PU
0
1
2
Our group will be presenting 8 papers at @emnlpmeeting , 3 papers at @NeurIPSConf , and 1 paper at NLP4DHπ€© Congratulation to all the authors and collaboratorsπ₯³πΊ
1
4
29
With Ears to See and Eyes to Hear: Sound Symbolism Experiments with Multimodal Large Language Models @tylerl404 @liyucheng_2 @chenghua_lin
https://t.co/Mt91Deenyz
#EMNLP2024
1
1
3
MMTE: Corpus and Metrics for Evaluating Machine Translation Quality of Metaphorical Language @SWangMB @tylerl404 @chenghua_lin
https://t.co/fr71VY9tVs
#EMNLP2024
1
2
3
Train & Constrain: Phonologically Informed Tongue-Twister Generation from Topics and Paraphrases @tylerl404 @chenghua_lin
https://t.co/JcacnhHrzZ
#CL #EMNLP2024
1
1
3
Check out Yiqi's work -- the first systematic research of the "self-preference" bias of LLMs as evaluators
[1/n] Do language model-driven evaluation metrics inherently favour texts generated by the same underlying model? Our #ACL2024 Findings paper ( https://t.co/rpjyiHEVrR) investigates this bias, focusing on metrics such as BARTScore, T5Score, and GPTScore in summarisation tasks. To
0
6
21
I think I kinda managed to bridge this? Idk, time will tell
0
0
2
When you get more than 1 person looking at your poster at a conference
0
55
699
Check out our MuPT: A Generative Symbolic Music Pretrained Transformer
MuPT: A Generative Symbolic Music Pretrained Transformer Presents a series of pre-trained models for symbolic music generation based on Llama architecture proj: https://t.co/xT0C4DsUGt abs: https://t.co/CmHbnHMhKG
1
6
9